skillify

skillify is a command for Claude Code from avelikiy/great_cto. It costs 41 tokens per session (1,343 once invoked), scanned A, original, MIT.

A command for turning a repeated work pattern into a reusable agent skill. It interviews the user and writes a SKILL.md file that records how agents should handle that pattern.

In plain words
What is it for?
Use it to identify recurring procedures, ask about when and how they should be used, and save the result as a reusable skill.
Why use it?
It prevents teams from repeatedly explaining the same multi-step process. The command looks for patterns that recur across sessions, logs, or agent work.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions subagents.

Part of the great-cto plugin — 40 skills, 44 commands, 72 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/avelikiy/great_cto/skillify
Clone the repo
git clone --depth 1 https://github.com/avelikiy/great_cto

Made for: Claude Code.

Or install great-cto, the plugin that ships this one along with the rest of its 40 skills, 44 commands, 72 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skillify

README.md
[![agentmods](https://agentmods.dev/badge/commands/avelikiy/great_cto/skillify.svg)](https://agentmods.dev/commands/avelikiy/great_cto/skillify)
Your own site
<a href="https://agentmods.dev/commands/avelikiy/great_cto/skillify"><img src="https://agentmods.dev/badge/commands/avelikiy/great_cto/skillify.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,343 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.01343
Opus 5 $0.00020 $0.00672
Sonnet 5 $0.00008 $0.00269
Haiku 4.5 $0.00004 $0.00134

Measured 2d ago against content hash 56ebf100da4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

skillify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/skillify.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Skillify command. Your job is to interview the user about a repeating pattern and codify it into a reusable SKILL.md file so agents learn the pattern permanently.

Trigger signal: same 5+ steps appearing 3+ times across sessions (look for it in session logs, agent outputs, or explicit user mention).

Step 1 — Identify the pattern

If $ARGUMENTS is provided, use it as the skill name/topic.

Otherwise, scan for candidates:

# Find repeated patterns in session logs
grep -h "Step\|1\.\|2\.\|3\." .great_cto/logs/session-*.md 2>/dev/null | sort | uniq -c | sort -rn | head -20
# Find repeated command sequences in lessons.md
cat .great_cto/lessons.md 2>/dev/null | head -50
# Recent agent outputs that looked procedural
ls .great_cto/verdicts/*.log 2>/dev/null | tail -5 | xargs grep -l "Step\|Procedure\|Checklist" 2>/dev/null

Present top 3 candidates to user. Ask: "Which pattern should I capture?"

Step 2 — Interview (one question at a time)

Ask these questions in order. Wait for an answer before asking the next.

Q1: "What triggers this pattern? Describe the situation where you'd reach for it — what keyword or signal in a request would make an agent apply this skill?"

Q2: "Walk me through the steps. Number them — I'll turn them into the skill body."

Q3: "What's the output? What artifact, verdict, or state change does completing this pattern produce?"

Q4: "Who runs this? Which agent(s) in the pipeline would apply it? (architect / pm / senior-dev / qa-engineer / security-officer / l3-support / devops / all)"

Q5: "What's the effort level? (low = <10 min of LLM work / medium = 10-30 min / high = >30 min)"

Q6: "Any anti-patterns — things this skill should actively prevent agents from doing?"

After all answers: show a draft and ask "Does this look right? Anything to add or change?"

Step 3 — Generate SKILL.md

Derive the skill slug from the name: lowercase, hyphen-separated, no special chars.

SKILL_NAME=$(echo "$ARGUMENTS" | tr '[:upper:]' '[:lower:]' | tr ' ' '-' | sed 's/[^a-z0-9-]//g')
SKILL_DIR="skills/$SKILL_NAME"
mkdir -p "$SKILL_DIR"

Read the full file on GitHub · 148 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 148 lines · 41 tokens per session scan A 56ebf100da4f

Subscribe to this mod's changes

skillify is a command published in the GitHub repository avelikiy/great_cto (89 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 1,343 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.